ignored the output from the test ecommerce site https://www.scrapingcourse.com/ecommerce/

.gitignore

@@ -0,0 +1,2 @@
+gscrape
+test-site

README

@@ -0,0 +1 @@
+This project was written ENTIRELY with AI

include/scraper.h

@@ -28,6 +28,6 @@ char *extract_h1(const char *html, size_t len);
  * Returns 0 and allocates *out on success (caller frees), or -1.
  * Each line represents one product; fields are separated by '|'.
  */
-int extract_products(const char *html, size_t len, char **out);
+int extract_products(const char *html, size_t len, const char *base_url, char **out);
 
 #endif /* SCRAPER_H */

src/main.c

@@ -12,24 +12,24 @@ static char *json_escape(const char *s) {
     size_t oi = 0;
     out[oi++] = '"';
     for (size_t i = 0; i < len; ++i) {
-        unsigned char c = s[i];
-        if (c == '"' || c == '\\') {
+        unsigned char uc = (unsigned char)s[i];
+        if (uc == '"' || uc == '\\') {
             if (oi + 2 >= cap) { cap *= 2; out = realloc(out, cap); }
             out[oi++] = '\\';
-            out[oi++] = c;
-        } else if (c == '\b') { if (oi + 2 >= cap) { cap *= 2; out = realloc(out, cap); } out[oi++] = '\\'; out[oi++] = 'b'; }
-        else if (c == '\f') { if (oi + 2 >= cap) { cap *= 2; out = realloc(out, cap); } out[oi++] = '\\'; out[oi++] = 'f'; }
-        else if (c == '\n') { if (oi + 2 >= cap) { cap *= 2; out = realloc(out, cap); } out[oi++] = '\\'; out[oi++] = 'n'; }
-        else if (c == '\r') { if (oi + 2 >= cap) { cap *= 2; out = realloc(out, cap); } out[oi++] = '\\'; out[oi++] = 'r'; }
-        else if (c == '\t') { if (oi + 2 >= cap) { cap *= 2; out = realloc(out, cap); } out[oi++] = '\\'; out[oi++] = 't'; }
-        else if (c < 0x20) {
-            char buf[7]; snprintf(buf, sizeof(buf), "\\u%04x", c);
+            out[oi++] = (char)uc;
+        } else if (uc == '\b') { if (oi + 2 >= cap) { cap *= 2; out = realloc(out, cap); } out[oi++] = '\\'; out[oi++] = 'b'; }
+        else if (uc == '\f') { if (oi + 2 >= cap) { cap *= 2; out = realloc(out, cap); } out[oi++] = '\\'; out[oi++] = 'f'; }
+        else if (uc == '\n') { if (oi + 2 >= cap) { cap *= 2; out = realloc(out, cap); } out[oi++] = '\\'; out[oi++] = 'n'; }
+        else if (uc == '\r') { if (oi + 2 >= cap) { cap *= 2; out = realloc(out, cap); } out[oi++] = '\\'; out[oi++] = 'r'; }
+        else if (uc == '\t') { if (oi + 2 >= cap) { cap *= 2; out = realloc(out, cap); } out[oi++] = '\\'; out[oi++] = 't'; }
+        else if (uc < 0x20) {
+            char buf[7]; snprintf(buf, sizeof(buf), "\\u%04x", (unsigned)uc);
             size_t bl = strlen(buf);
             if (oi + bl + 1 >= cap) { cap = cap + bl + 16; out = realloc(out, cap); }
             memcpy(out + oi, buf, bl); oi += bl;
         } else {
             if (oi + 1 >= cap) { cap *= 2; out = realloc(out, cap); }
-            out[oi++] = c;
+            out[oi++] = (char)uc;
         }
     }
     if (oi + 2 >= cap) { cap += 2; out = realloc(out, cap); }
@@ -52,7 +52,7 @@ static void print_kv_json(const char *kv_lines) {
                 size_t keylen = (size_t)(sep - p);
                 const char *vstart = sep + 1;
                 while (vstart < p + linelen && (*vstart == ' ' || *vstart == '\t')) vstart++;
-                size_t vallen = (p + linelen) - vstart;
+                size_t vallen = (size_t)((p + linelen) - vstart);
                 char *key = malloc(keylen + 1);
                 char *val = malloc(vallen + 1);
                 memcpy(key, p, keylen); key[keylen] = '\0';
@@ -93,7 +93,7 @@ static void print_products_json(const char *products_lines) {
                 size_t plen = (size_t)(s2 - p2);
                 const char *u2 = s2 + 1;
                 while (u2 < p + linelen && (*u2 == ' ' || *u2 == '\t')) u2++;
-                size_t ulen = (p + linelen) - u2;
+                size_t ulen = (size_t)((p + linelen) - u2);
                 name = malloc(nlen + 1); memcpy(name, p, nlen); name[nlen] = '\0';
                 price = malloc(plen + 1); memcpy(price, p2, plen); price[plen] = '\0';
                 url = malloc(ulen + 1); memcpy(url, u2, ulen); url[ulen] = '\0';
@@ -103,7 +103,7 @@ static void print_products_json(const char *products_lines) {
                 const char *p2 = s1 + 1;
                 while (nlen > 0 && (p[nlen-1] == ' ' || p[nlen-1] == '\t')) nlen--;
                 while (p2 < p + linelen && (*p2 == ' ' || *p2 == '\t')) p2++;
-                size_t plen = (p + linelen) - p2;
+                size_t plen = (size_t)((p + linelen) - p2);
                 name = malloc(nlen + 1); memcpy(name, p, nlen); name[nlen] = '\0';
                 price = malloc(plen + 1); memcpy(price, p2, plen); price[plen] = '\0';
                 url = strdup("");
@@ -202,7 +202,7 @@ int main(int argc, char **argv) {
     }
 
     char *products = NULL;
-    if (extract_products(html, html_len, &products) == 0 && products) {
+    if (extract_products(html, html_len, url, &products) == 0 && products) {
         printf("\"products\":");
         print_products_json(products);
         free(products);

src/scraper.c

@@ -390,7 +390,7 @@ static char *find_price_in_node(xmlNode *node) {
                 if (xmlStrcasecmp(cur->name, (const xmlChar *)"a") != 0 &&
                     xmlStrcasecmp(cur->name, (const xmlChar *)"h1") != 0 &&
                     xmlStrcasecmp(cur->name, (const xmlChar *)"h2") != 0 &&
-                    (strchr(txt, '$') || strchr(txt, '£') || strchr(txt, '€') || strstr(txt, "USD") || strstr(txt, "EUR"))) {
+                    (strchr(txt, '$') || strstr(txt, "£") || strstr(txt, "€") || strstr(txt, "USD") || strstr(txt, "EUR"))) {
                     if (strlen(txt) < 200) {
                         char *trim = strdup(txt);
                         free(txt);
@@ -411,7 +411,61 @@ static char *find_price_in_node(xmlNode *node) {
  * Looks for h2.product-name and span.price preferentially, falls back to
  * generic name/price finders.
  */
-static void collect_product_from_node(xmlNode *node, char **out, size_t *out_len, int *found) {
+/* Resolve a possibly-relative href against a base URL. Returns a newly
+ * allocated string (caller must free) or NULL on error.
+ */
+static char *resolve_url(const char *base, const char *href) {
+    if (!href) return NULL;
+    if (strstr(href, "://")) return strdup(href);
+    if (strncmp(href, "//", 2) == 0) {
+        /* scheme-relative */
+        const char *p = strstr(base, "://");
+        if (!p) return strdup(href + 2);
+        size_t scheme_len = (size_t)(p - base);
+        size_t outlen = scheme_len + 3 + strlen(href + 2) + 1;
+        char *out = malloc(outlen);
+        if (!out) return NULL;
+        snprintf(out, outlen, "%.*s://%s", (int)scheme_len, base, href + 2);
+        return out;
+    }
+
+    if (href[0] == '/') {
+        /* absolute path on same host */
+        const char *p = strstr(base, "://");
+        const char *start = base;
+        if (p) start = p + 3; /* host start */
+        const char *host_end = strchr(start, '/');
+        size_t prefix_len = 0;
+        if (host_end) prefix_len = (size_t)(host_end - base);
+        else prefix_len = strlen(base);
+        size_t outlen = prefix_len + strlen(href) + 1;
+        char *out = malloc(outlen);
+        if (!out) return NULL;
+        memcpy(out, base, prefix_len);
+        out[prefix_len] = '\0';
+        strncat(out, href, strlen(href));
+        return out;
+    }
+
+    /* relative path: append after last '/' in base */
+    const char *last_slash = strrchr(base, '/');
+    size_t base_prefix = strlen(base);
+    if (last_slash) {
+        /* keep up to and including last slash */
+        base_prefix = (size_t)(last_slash - base + 1);
+    } else {
+        base_prefix = strlen(base);
+    }
+    size_t outlen = base_prefix + strlen(href) + 1;
+    char *out = malloc(outlen);
+    if (!out) return NULL;
+    memcpy(out, base, base_prefix);
+    out[base_prefix] = '\0';
+    strncat(out, href, strlen(href));
+    return out;
+}
+
+static void collect_product_from_node(xmlNode *node, char **out, size_t *out_len, int *found, const char *base_url) {
     if (!node) return;
     char *name = NULL;
     char *price = NULL;
@@ -460,6 +514,15 @@ static void collect_product_from_node(xmlNode *node, char **out, size_t *out_len
     /* find product link if available */
     plink = find_href_in_node(node);
     if (!plink) plink = strdup("<no-link>");
+    else {
+        if (base_url) {
+            char *abs = resolve_url(base_url, plink);
+            if (abs) {
+                free(plink);
+                plink = abs;
+            }
+        }
+    }
 
     if (name || price) {
         if (!name) name = strdup("<no-name>");
@@ -472,7 +535,7 @@ static void collect_product_from_node(xmlNode *node, char **out, size_t *out_len
     free(plink);
 }
 
-static void traverse_and_collect_products(xmlNode *node, char **out, size_t *out_len, int *found) {
+static void traverse_and_collect_products(xmlNode *node, char **out, size_t *out_len, int *found, const char *base_url) {
     for (xmlNode *cur = node; cur; cur = cur->next) {
         if (cur->type != XML_ELEMENT_NODE) continue;
 
@@ -486,18 +549,18 @@ static void traverse_and_collect_products(xmlNode *node, char **out, size_t *out
         else if (cls && xmlStrcasecmp(cur->name, (const xmlChar *)"li") == 0 && attr_contains(cls, "product")) is_product = true;
 
         if (is_product) {
-            collect_product_from_node(cur, out, out_len, found);
+            collect_product_from_node(cur, out, out_len, found, base_url);
         }
 
         if (data_products) xmlFree(data_products);
         if (itemtype) xmlFree(itemtype);
         if (cls) xmlFree(cls);
 
-        if (cur->children) traverse_and_collect_products(cur->children, out, out_len, found);
+        if (cur->children) traverse_and_collect_products(cur->children, out, out_len, found, base_url);
     }
 }
 
-int extract_products(const char *html, size_t len, char **out) {
+int extract_products(const char *html, size_t len, const char *base_url, char **out) {
     if (!html || len == 0 || !out) return -1;
     htmlDocPtr doc = htmlReadMemory(html, (int)len, NULL, NULL, HTML_PARSE_NOERROR | HTML_PARSE_NOWARNING);
     if (!doc) return -1;
@@ -507,7 +570,7 @@ int extract_products(const char *html, size_t len, char **out) {
     size_t out_len = 0;
     int found = 0;
 
-    traverse_and_collect_products(root, out, &out_len, &found);
+    traverse_and_collect_products(root, out, &out_len, &found, base_url);
 
     xmlFreeDoc(doc);
     xmlCleanupParser();